Phase-Based Latency Mitigation in LLM-Driven VR Agents

ACM Symposium on Applied Perception, pp. 1–2

Abstract

Response latency in Large Language Model (LLM)–driven Embodied Conversational Agents (ECAs) can disrupt conversational flow. We investigated whether phase-specific multimodal feedback can mitigate perceived waiting time without modifying the underlying dialogue pipeline. In a within-subjects study (n = 35), participants experienced feedback during user speech (USP), the response-waiting phase (RWP), both phases, or neither phase. Results showed that RWP feedback consistently reduced perceived latency, whereas USP-only feedback showed weaker and partly distracting effects, while perceived social qualities remained unaffected in all conditions. This highlights the importance of temporally aligned feedback for improving perceived responsiveness.

Authors 4

1. Konstantin W. Kühlem Aachen Visual Computing Institute

   RWTH Aachen University

   Affiliation as printed

   Visual Computing Institute, RWTH Aachen University, Aachen, Germany

2. Ying Zhou Aachen Faculty of Computer Science

   RWTH Aachen University

   Affiliation as printed

   Faculty of Computer Science, RWTH Aachen University, Aachen, Germany

3. Torsten Kuhlen Aachen Visual Computing Institute

   RWTH Aachen University

   Affiliation as printed

   Visual Computing Institute, RWTH Aachen University, Aachen, Germany

4. Andrea Bönsch Aachen Visual Computing Institute

   RWTH Aachen University

   Affiliation as printed

   Visual Computing Institute, RWTH Aachen University, Aachen, Germany